摘要
为提高变压器故障诊断准确率,提出了一种基于遗传算法的动态加权模糊C均值聚类算法。该算法使用把聚类中心作为染色体的浮点数的编码方式,染色体长度可变,不同的长度对应于不同的故障聚类数;并使用权值区别不同样本点对故障划分的影响程度。将该算法应用于电力变压器油中溶解气体分析(DGA)数据分析,实现了变压器的故障诊断。经过大量实例分析,并将结果与其他算法进行对比,表明该算法具有较高的诊断精度。
ABSTRACT：In order to improve the correct rate of fault diagnosis of transformer, this paper investigates a dynamic weighted fuzzy c-means clustering algorithm based on genetic algorithm. The algorithm adopts a kind of cluster-center-based floating point encoding mode, in which the variable length chromosomes express cluster prototypes and different length of chromosomes corresponding to different numbers of cluster prototypes;besides,The algorithm utilizes the weights to express the relative degree of the importance of various data in fault partitioning. The algorithm is applied to DGA data analysis, which can accomplish fault diagnosis of the transformer. Examples analysis and comparison results show that the preci-sion of fault diagnosis can be evidently improved.
出处
《电网与清洁能源》
北大核心
2016年第4期89-92,共4页
Power System and Clean Energy
关键词
动态聚类
权值
遗传算法
变压器
故障诊断
dynamic clustering
weights
genetic algori-thm
transformer
fault diagnosis
